Language model learning system, language model learning method, and language model learning program

Abstract

A language model learning system for learning a language model on an identifiable basis relating to a word error rate used in speech recognition. The language model learning system (10) includes a recognizing device (101) for recognizing an input speech by using a sound model and a language model and outputting the recognized word sequence as the recognition result, a reliability degree computing device (103) for computing the degree of reliability of the word sequence, and a language model parameter updating device (104) for updating the parameters of the language model by using the degree of reliability. The language model parameter updating device updates the parameters of the language model to heighten the degree of reliability of the word sequence the computed degree of reliability of which is low when the recognizing device recognizes by using the updated language model and the reliability degree computing device computes the degree of reliability.

Description

CROSS REFERENCE TO RELATED APPLICATION[0001]This application is based upon and claims the benefit of priority from Japanese patent application No. 2006-150962, filed on May 31, 2006, the disclosure of which is incorporated herein in its entirety by reference.TECHNICAL FIELD[0002]The present invention relates to a language model learning system, a language model learning method, and a language model learning program used in speech recognition. More specifically, the present invention relates to a language model learning system, a language model learning method, and a language model learning program, which are capable of building a language model of higher accuracy than a conventional method since the present invention executes learning of a language model by using discriminative bases, and are capable of building a speech recognition system of higher accuracy by utilizing the language model of the higher accuracy for the speech recognition system.BACKGROUND ART[0003]A language model ...

AI Technical Summary

Benefits of technology

[0021]Like the language model learning system, it is possible with the above-described language model learning program to build the language model of high reliability by enabling the computer to execute the language model parameter updating processing according to the discriminative bases that are related to the bases that are used for the evaluation of the speech recognition. Therefore, highly accurate speech recognition can be ...

Problems solved by technology

A first issue regarding the conventional language model learning system is that it may not be able to obtain highly reliable recognition results even when speech recognition is conducted based on the language model that is learned by the conventional method, since the most likelihood estimation that is the conventional language model learning method takes no consideration over a word error rate and the like whi...

Images